A Neural-based Bio-regionalization of the Mediterranean Sea using Satellite and Argo-Float Records.

We present a partitioning of the Mediterranean Sea into regions having well defined characteristics with respect to sea-surface temperature and surface chlorophyll-a concentration observed by satellite and by the Argo mixed-layer depth. This regionalization was performed using an innovative classification based on neural networks, the so-called 2S-SOM. Its major advantage is to consider the specificity of the variables by adding specific weights to each of them, which facilitates the classification and consequently highlights the regional correlations. The 2S-SOM provided a well differentiated regionalization of the Mediterranean Sea waters into seven bioregions governed by specific physical and biogeochemical processes.

[1]  Sylvie Thiria,et al.  The Sicily Channel surface circulation revisited using a neural clustering analysis of a high‐resolution simulation , 2016 .

[2]  B. Gentili,et al.  The Mediterranean Sea: a miniature ocean for climatic and environmental studies and a key for the climatic functioning of the North Atlantic , 1999 .

[3]  S. Somot,et al.  The Biodiversity of the Mediterranean Sea: Estimates, Patterns, and Threats , 2010, PloS one.

[4]  S. Thiria,et al.  Phytoplankton Diversity in the Mediterranean Sea From Satellite Data Using Self‐Organizing Maps , 2019, Journal of Geophysical Research: Oceans.

[5]  P. Chevaldonné,et al.  Climate change effects on a miniature ocean: the highly diverse, highly impacted Mediterranean Sea. , 2010, Trends in ecology & evolution.

[6]  Tereza Cavazos.  Large-scale circulation anomalies conducive to extreme precipitation events and derivation of daily rainfall in northeastern Mexico and southeastern Texas , 1999 .

[7]  E. Ser-Giacomi,et al.  Hydrodynamic provinces and oceanic connectivity from a transport network help designing marine reserves , 2014, 1407.6920.

[8]  S. Thiria,et al.  Inferring the seasonal evolution of phytoplankton groups in the Senegalo‐Mauritanian upwelling region from satellite ocean‐color spectral measurements , 2015 .

[9]  F. d’Ovidio,et al.  Mixing structures in the Mediterranean Sea from finite‐size Lyapunov exponents , 2004, nlin/0404041.

[10]  Christopher N. K. Mooers,et al.  Performance evaluation of the self‐organizing map for feature extraction , 2006 .

[11]  Dean Roemmich,et al.  An Argo mixed layer climatology and database , 2017 .

[12]  A. Longhurst.  Ecological Geography of the Sea , 1998 .

[13]  Lynne D. Talley,et al.  A New Algorithm for Finding Mixed Layer Depths with Applications to Argo Data and Subantarctic Mode Water Formation , 2009 .

[14]  Anthony J. Richardson,et al.  Using self-organizing maps to identify patterns in satellite imagery , 2003 .

[15]  Mory Ouattara,et al.  Développement et mise en place d'une méthode de classification multi-blocs : application aux données de l'OQAI. (Development and implementation of a multi-block clustering methods : apply to OQAI data sets) , 2014 .

[16]  Robert H. Weisberg,et al.  Patterns of ocean current variability on the West Florida Shelf using the self-organizing map , 2005 .

[17]  Teuvo Kohonen,et al.  Essentials of the self-organizing map , 2013, Neural Networks.

[18]  L. Houpert,et al.  The Mediterranean subsurface phytoplankton dynamics and their impact on Mediterranean bioregions , 2018 .

[19]  F. D’Ortenzio,et al.  Interannual variability of the Mediterranean trophic regimes from ocean color satellites , 2015 .

[20]  Sylvie Thiria,et al.  Analysis of the Senegalo-Mauritanian upwelling by processing satellite remote sensing observations with topological maps. , 2009, 2009 International Joint Conference on Neural Networks.

[21]  B. Hewitson,et al.  Self-organizing maps: applications to synoptic climatology , 2002 .

[22]  Julien Palmiéri.  Modélisation biogéochimique de la mer Méditerranée avec le modèle régional couplé NEMO-MED12/PISCES , 2014 .

[23]  A. Saliot.  The Mediterranean Sea , 2005 .

[24]  Bryan A. Franz,et al.  Chlorophyll aalgorithms for oligotrophic oceans: A novel approach based on three‐band reflectance difference , 2012 .

[25]  F. D’Ortenzio,et al.  On the trophic regimes of the Mediterranean Sea: a satellite analysis , 2008 .

[26]  Jennifer L. Molnar,et al.  Marine Ecoregions of the World: A Bioregionalization of Coastal and Shelf Areas , 2007 .

[27]  S. Thiria,et al.  Estimation of Secondary Phytoplankton Pigments From Satellite Observations Using Self‐Organizing Maps (SOMs) , 2019, Journal of Geophysical Research: Oceans.

[28]  G. Reygondeau,et al.  Defining Mediterranean and Black Sea Biogeochemical Subprovinces and Synthetic Ocean Indicators Using Mesoscale Oceanographic Features , 2014, PloS one.

[29]  G. Reygondeau,et al.  Biogeochemical regions of the Mediterranean Sea: An objective multidimensional and multivariate environmental approach , 2017 .

[30]  P. Minnett,et al.  A decade of sea surface temperature from MODIS , 2015 .

[31]  T. Platt,et al.  An estimate of global primary production in the ocean from satellite radiometer data , 1995 .

[32]  S. Thiria,et al.  Estimation of phytoplankton pigments from ocean-color satellite observations in the Senegalo–Mauritanian region by using an advanced neural classifier , 2019, Ocean Science.

[33]  Fouad Badran,et al.  Automatic neural classification of ocean colour reflectance spectra at the top of the atmosphere with introduction of expert knowledge , 2003 .